Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Pavllo, Dario"'
Autor:
Anagnostidis, Sotiris, Pavllo, Dario, Biggio, Luca, Noci, Lorenzo, Lucchi, Aurelien, Hofmann, Thomas
Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the seq
Externí odkaz:
http://arxiv.org/abs/2305.15805
Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction in the area of 3D reconstruction from a single view, owing to their ability to efficiently model arbitrary topologies. Recent work in this area, however, has mostly focus
Externí odkaz:
http://arxiv.org/abs/2211.11674
Autor:
Sheebaelhamd, Ziyad, Zisis, Konstantinos, Nisioti, Athina, Gkouletsos, Dimitris, Pavllo, Dario, Kohler, Jonas
Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, however, typically come with critical safety constraints that must not be v
Externí odkaz:
http://arxiv.org/abs/2108.03952
This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks. Leveraging an in-depth analysis of neural chains, we first show that vanishing gradients cannot be circumvented when
Externí odkaz:
http://arxiv.org/abs/2106.03763
Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle pose and appearance, enable downstream applications in computer graphic
Externí odkaz:
http://arxiv.org/abs/2103.15627
While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such mo
Externí odkaz:
http://arxiv.org/abs/2006.07660
Autor:
Dhall, Ankit, Makarova, Anastasia, Ganea, Octavian, Pavllo, Dario, Greeff, Michael, Krause, Andreas
Image classification has been studied extensively, but there has been limited work in using unconventional, external guidance other than traditional image-label pairs for training. We present a set of methods for leveraging information about the sema
Externí odkaz:
http://arxiv.org/abs/2004.03459
We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as textual des
Externí odkaz:
http://arxiv.org/abs/1912.03161
Publikováno v:
International Journal of Computer Vision (Special Issue on Machine Vision with Deep Learning), 2019. Online ISSN: 1573-1405
Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angles or
Externí odkaz:
http://arxiv.org/abs/1901.07677
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised trai
Externí odkaz:
http://arxiv.org/abs/1811.11742